In repeated-measures models, baseline values of outcomes were used as covariates. Subsequent analyses were adjusted for additional baseline characteristics. For HbA^sub 1c^, models were adjusted for age, sex, duration of diabetes, and change in diabetes medications. For weight and waist circumference, models were adjusted for age, sex, and smoking. Adjusting for these covariates did not affect the results for comparing treatment groups. Secondary analyses were adjusted for use of outside behavioral resources, but this did not alter results. Statistical analyses were performed using SAS statistical software (version 8.2; SAS Institute, Cary, NC).